{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H6ZN4GPOK4AAV52YAPVIAEZZNH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dbf5c8fdd875a506912cb1a7727e6ed4ab37f900644193aa1782a936230a65e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T09:15:44Z","title_canon_sha256":"8b1fcbde56ae445804d87363a01e458cd3880bb6b1417693e7593ef2bc55695e"},"schema_version":"1.0","source":{"id":"2406.04770","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04770","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04770v2","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04770","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"pith_short_12","alias_value":"H6ZN4GPOK4AA","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"pith_short_16","alias_value":"H6ZN4GPOK4AAV52Y","created_at":"2026-07-05T09:16:17Z"},{"alias_kind":"pith_short_8","alias_value":"H6ZN4GPO","created_at":"2026-07-05T09:16:17Z"}],"graph_snapshots":[{"event_id":"sha256:2939bd862d1e877fbf995512982373988e6591ed6c3af6f7581faf910a61b1db","target":"graph","created_at":"2026-07-05T09:16:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.04770/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce WildBench, an automated evaluation framework designed to benchmark large language models (LLMs) using challenging, real-world user queries. WildBench consists of 1,024 tasks carefully selected from over one million human-chatbot conversation logs. For automated evaluation with WildBench, we have developed two metrics, WB-Reward and WB-Score, which are computable using advanced LLMs such as GPT-4-turbo. WildBench evaluation uses task-specific checklists to evaluate model outputs systematically and provides structured explanations that justify the scores and comparisons, resulting i","authors_text":"Abhilasha Ravichander, Bill Yuchen Lin, Faeze Brahman, Khyathi Chandu, Nouha Dziri, Ronan Le Bras, Valentina Pyatkin, Yejin Choi, Yuntian Deng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T09:15:44Z","title":"WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04770","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b8f6b4e9ff3d0578c30414f3c20141d7ed4cd20c4e1f936c3a451c4b7f50c0e9","target":"record","created_at":"2026-07-05T09:16:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dbf5c8fdd875a506912cb1a7727e6ed4ab37f900644193aa1782a936230a65e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T09:15:44Z","title_canon_sha256":"8b1fcbde56ae445804d87363a01e458cd3880bb6b1417693e7593ef2bc55695e"},"schema_version":"1.0","source":{"id":"2406.04770","kind":"arxiv","version":2}},"canonical_sha256":"3fb2de19ee57000af75803ea80133969d5c55c6e513e8718907ff207aa1f920e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fb2de19ee57000af75803ea80133969d5c55c6e513e8718907ff207aa1f920e","first_computed_at":"2026-07-05T09:16:17.675253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:17.675253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NHbtlwPsWXIV3FV1kU4loj0V6VQI89NvGyOz4QR1H9l4dzaG13Qy9mQV6/1noNMXETYEi05y1aIdF1Aa0gPSBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:17.675844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04770","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8f6b4e9ff3d0578c30414f3c20141d7ed4cd20c4e1f936c3a451c4b7f50c0e9","sha256:2939bd862d1e877fbf995512982373988e6591ed6c3af6f7581faf910a61b1db"],"state_sha256":"0fdc6fd4d9ad7e7955d33f535876c2b75bb20925b8eee3f9c2d6ae085f58b4e3"}